Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    dialogue or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Dialogue or quotations

    np_acts-logits-general · gemini-2.0-flash

    responses to questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.64
    WithIOException
    -0.61
    /*---
    -0.61
     الحره
    -0.61
    — 
    -0.60
    WriteTagHelper
    -0.59
     المعيارى
    -0.59
    ("-");
    -0.57
     }}}{
    -0.56
     }}-
    -0.55
    POSITIVE LOGITS
    But
    0.82
    No
    0.82
    Yes
    0.81
    Exactly
    0.74
    So
    0.74
    Oh
    0.73
     Yes
    0.73
    Yeah
    0.72
    Not
    0.71
     Exactly
    0.71
    Act Density 0.155%

    No Known Activations